Content
61%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, highly actionable skill with real CLI commands, configs, and code covering the main Shopify surfaces, backed by genuine one-level-deep reference files. The main weaknesses are an implicit rather than explicit development workflow (no validation checkpoints), inline GraphQL blocks that duplicate the references, and one non-runnable code example.
Suggestions
Add an explicit stepwise app workflow with validation checkpoints, e.g.: 1. 'shopify app init' 2. configure scopes in shopify.app.toml 3. 'shopify app dev' → verify the tunnel loads 4. test webhook HMAC validation locally 5. only then 'shopify app deploy'.
Move the full GraphQL query blocks into 'references/app-development.md' and keep one compact example inline, trimming the duplicated material and the filler 'When to Use' sentence.
Fix the checkout extension example to import 'useState' and 'useEffect' from 'react' so it is copy-paste executable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean commands and code with almost no concept explanations Claude already knows, but it can be tightened: ~90 lines of full GraphQL queries duplicate material in 'references/app-development.md', the API version '2026-01' is pinned twice in the body (time-sensitive detail not in a deprecated/old-patterns section), and the trailing 'When to Use' sentence ('This skill is applicable to execute the workflow or actions described in the overview.') is pure filler. This fits anchor 3 (mostly efficient, some tightening possible) better than 4, whose 'minor instances' understates the inlined query blocks. | 3 / 5 |
Actionability | Guidance is highly executable: install/init/deploy CLI commands, TOML access-scope and webhook configs, complete GraphQL queries with a variables example, a working Liquid snippet, and IF/→ troubleshooting steps. It falls just short of anchor 5 because the checkout extension example uses 'useState' and 'useEffect' without importing them, so that block is not copy-paste runnable — a concrete minor gap matching anchor 4. | 4 / 5 |
Workflow Clarity | The ROUTING section is a clear IF/→ decision tree and the CLI section implies a sequence (init → dev → deploy), but no explicit ordered workflow with validation checkpoints exists (e.g., verify the dev tunnel, confirm scopes granted, test webhook delivery before deploy). This matches anchor 3 (sequence present/implicit, checkpoints missing); it is not 4 because 'most checkpoints present' is not met, and not 2 because the routing and troubleshooting sections give coherent, well-defined structure. | 3 / 5 |
Progressive Disclosure | Good structure: a routing table pointing to the three real one-level-deep reference files (verified present: app-development.md, extensions.md, themes.md), a 'Reference Files' section describing each file's contents, and documented scripts. It is not 5 because some reference-level material (full GraphQL queries) is inlined in SKILL.md instead of being pointed to, and the 'scripts/tests' directory is never mentioned — minor organization gaps matching anchor 4. | 4 / 5 |
Total | 14 / 20 Passed |